Moving Out: Physically-grounded Human-AI Collaboration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kang, Xuhui, Lee, Sung-Wook, Liu, Haolin, Wang, Yuyan, Kuo, Yen-Ling
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918149572526080
author Kang, Xuhui
Lee, Sung-Wook
Liu, Haolin
Wang, Yuyan
Kuo, Yen-Ling
author_facet Kang, Xuhui
Lee, Sung-Wook
Liu, Haolin
Wang, Yuyan
Kuo, Yen-Ling
contents The ability to adapt to physical actions and constraints in an environment is crucial for embodied agents (e.g., robots) to effectively collaborate with humans. Such physically grounded human-AI collaboration must account for the increased complexity of the continuous state-action space and constrained dynamics caused by physical constraints. In this paper, we introduce Moving Out, a new human-AI collaboration benchmark that resembles a wide range of collaboration modes affected by physical attributes and constraints, such as moving heavy items together and maintaining consistent actions to move a big item around a corner. Using Moving Out, we designed two tasks and collected human-human interaction data to evaluate models' abilities to adapt to diverse human behaviors and unseen physical attributes. To address the challenges in physical environments, we propose a novel method, BASS (Behavior Augmentation, Simulation, and Selection), to enhance the diversity of agents and their understanding of the outcome of actions. Our experiments show that BASS outperforms state-of-the-art models in AI-AI and human-AI collaboration. The project page is available at https://live-robotics-uva.github.io/movingout_ai/.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18623
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Moving Out: Physically-grounded Human-AI Collaboration
Kang, Xuhui
Lee, Sung-Wook
Liu, Haolin
Wang, Yuyan
Kuo, Yen-Ling
Machine Learning
Artificial Intelligence
Multiagent Systems
The ability to adapt to physical actions and constraints in an environment is crucial for embodied agents (e.g., robots) to effectively collaborate with humans. Such physically grounded human-AI collaboration must account for the increased complexity of the continuous state-action space and constrained dynamics caused by physical constraints. In this paper, we introduce Moving Out, a new human-AI collaboration benchmark that resembles a wide range of collaboration modes affected by physical attributes and constraints, such as moving heavy items together and maintaining consistent actions to move a big item around a corner. Using Moving Out, we designed two tasks and collected human-human interaction data to evaluate models' abilities to adapt to diverse human behaviors and unseen physical attributes. To address the challenges in physical environments, we propose a novel method, BASS (Behavior Augmentation, Simulation, and Selection), to enhance the diversity of agents and their understanding of the outcome of actions. Our experiments show that BASS outperforms state-of-the-art models in AI-AI and human-AI collaboration. The project page is available at https://live-robotics-uva.github.io/movingout_ai/.
title Moving Out: Physically-grounded Human-AI Collaboration
topic Machine Learning
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2507.18623